Big news: Tryolabs joins Qubika. Same teams, broader set of combined capabilities. Read now ->

Case study

Product categorization with Machine Learning

Categorization has become much more efficient and we implemented some automation of category creation and product classification.

Industry: Retail & ecommerce
Client
Solution: NLP

Product categorization with Machine Learning

Efficiency and automation boost

MercadoLibre is the largest online retailer in Latin America with over 100M users. It is an e-commerce and auction platform that provides users with buying and selling mechanisms for e-transactions. We established a working relationship with them in order to solve issues related to the category tree of their product catalog.

Challenge

E-commerce businesses spend a considerable amount of time and effort in organizing their products. MercadoLibre has a vast catalog, lots of data that needs to be archived and correctly analyzed. They wanted to explore a solution that makes that category tree more efficient and examine ways of automating this process.

Solution

An iteration based on specific goal achievement, ongoing development and progressive team scaling were the basis from which this solution was crafted. Classifying products into a set of known categories by using supervised learning.

-80% cost

item categorization

Discover our approach

The problem was faced in three stages: Research & Development, bringing the model into production, and exposing it through an API and Frontend development.

R&D implied a massive historical data analysis which later directed us to the hypothesis, trial & error circle until a fair solution was found.

We built an algorithm that uses neural networks and users' navigation data to facilitate item categorization. We also developed a set of algorithms using deep learning and NLP tools to suggest missing categories automatically. Some of the tools used where Gensim, Keras, and NLTK.

As human validation is part of the solution, we built an ultra-intuitive and intelligent frontend using React + Redux, ES6, and Webpack to communicate with the built API.

Tryolabs has been a key piece in optimizing and extending our category trees at a much higher pace than we could achieve with our former tools and teams. Through the mastering and customization of state of the art Machine Learning techniques, we've been able to increase item "findability" and conversion rates. We are so glad to have them collaborating with us in the quest for the best e-commerce solution. I would absolutely recommend them.

Diego Cabrera, Senior Manager | Mercado Libre

Discover how the world’s leading enterprises partner with Tryolabs for building data-driven solutions that boost their KPIs.